Triple
T6364958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tahkuna Lighthouse |
E143201
|
entity |
| Predicate | hasAdjacentStructures |
P22388
|
FINISHED |
| Object | keeper’s house |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: keeper’s house | Statement: [Tahkuna Lighthouse, hasAdjacentStructures, keeper’s house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdjacentStructures Context triple: [Tahkuna Lighthouse, hasAdjacentStructures, keeper’s house]
-
A.
hasStructureOnOrAdjacent
chosen
Indicates that one entity has a physical structure located on it or immediately next to it.
-
B.
isAdjacentTo
Indicates that one entity is directly next to or bordering another without anything of the same type in between.
-
C.
hasAdjacentUse
Indicates that one entity is used or occurs directly next to another in space, time, or sequence.
-
D.
hasStructureAbove
Indicates that one entity has another entity positioned vertically higher or located on top of it within a structural or spatial arrangement.
-
E.
hasHumanStructure
Indicates that one entity possesses or exhibits a structural form or organization characteristic of humans.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c008d8c61081908bcaf61510d881ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0680ed0148190b6e310b15b3449ff |
completed | March 22, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69c060ee055081908c79a1d151bd74cd |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:32 p.m.